How to build a chatbot

Chatbots interpret and process a user's words or phrases and give an answer. They can provide responses based on a combination of predefined scripts and machine learning applications.

You can build your first chatbot through our tutorial in only 10 minutes.

Through the Integrations tab of your assistant, you can copy and paste a JavaScript snippet into your existing website’s HTML. This will create a fully customizable web widget on your desired page. You can also integrate Watson Assistant into WhatsApp, Facebook Messenger, Alexa and CRM systems. And of course, our chatbot API integrates with other Watson APIs.

The component where you build the conversation that the chatbot has with your users. Dialog gives the user a clear understanding of what the chatbot is there to do and allows the chatbot to define user intent and provide a pre-authored response.

Anything the user inputs into a chatbot which is then used to derive intent. If a user types “What are your office hours?”, the entire sentence is an utterance.

Chatbots use natural language processing (NLP). Natural language processing makes it possible for your bot to read text, hear and interpret speech, measure sentiment and determine which parts are important.

You can start with our Lite plan at no cost or explore our Plus and Enterprise plans to enhance your chatbot’s capabilities.

The primary difference between a chatbot and a virtual agent is the chatbot’s inability to learn. A chatbot can provide clear pre-written answers, but a virtual agent like Watson Assistant, uses AI to interpret a question and determine what the user really needs to know.

Chatbots can learn by analyzing data you provide, and through the dialog with your users. Chatbots can also learn by having a human editing the system. In most cases, both are required.

To accurately interpret a user’s intent and maintain the context of the dialog, to provide the user with accurate and relevant information, and to be indistinguishable from a human interaction.

Chatbots are often associated with customer support and customer experience. IBM customers have used chatbots in a range of use cases – including engaging with customers for customer self-service, automating backend processes, optimizing workflows and more.

Yes, you can use this Wordpress plugin (link resides outside IBM). In a few minutes, you can train Watson to answer FAQs, provide useful information and help customers navigate your website.

Watson Assistant uses machine learning and intent detection algorithms to understand how to answer end-user questions accurately. The artificial intelligence at the core of Watson Assistant is designed to correctly identify the countless permutations of intent in real-world interactions. In short, we designed Watson Assistant to be easy to train and to recognize accurately what the user wants.

Add a text messaging integration so your assistant can exchange messages with your customers. You can learn how, and to watch a video that walks through the setup process, see Phone and SMS Integration in the IBM Watson Apps Community.

Containment is the number of conversations in which the assistant is able to satisfy the customer's request without human agent intervention.

Coverage is the number of conversations in which the assistant is confident that it can address a customer's request.